基于聚类的血清质谱数据和体检数据关联规则分析  

Association Rule Analysis of Serum Mass Spectrometry Data and Physical Examination Data Based on Clustering

作　　者：王玉 韩家新[1] Wang Yu;Han Jiaxin(College of Computer,Xi’an Shiyou University,Xi’an 710065)

机构地区：[1]西安石油大学计算机学院,西安710065

出　　处：《现代计算机》2022年第23期55-59,共5页Modern Computer

摘　　要：近年来,公众健康问题成为人们关注的热点,体检数据和血清质谱数据都是通过血液样本得到的,如何快速从血液数据中获得想要的信息成为一个问题。质谱数据具有维度高,且各组数据维度不一致的特点,单靠人工难以从中提取并分析信息。随着数据挖掘中关联规则分析方法的不断进步,可以通过对血清数据进行数据挖掘找到血清之间的关联信息,从而快速得到血清数据分析结果。提出一种改进K-means算法,并用对数据进行聚类,聚类后的数据具有簇内差异小,簇间差异大的特点,能更好地对连续数据进行离散化,Apriori算法和FP-Growth算法分析得到血清质谱数据和体检数据关联规则,此关联规则可以验证血液检测结果的准确性,对于医学血液检测的发展有重大意义。In recent years, public health issues have become a focus of attention. Physical examination data and serum mass spectrometry data are obtained from blood samples. How to quickly obtain the desired information from blood data has become a problem. Mass spectrometry data is characterized by high dimensions and inconsistent dimensions of each group of data, so it is difficult to extract and analyze information from it manually. With the continuous progress of association rule analysis methods in data mining, find the association information between sera through data mining on serum data, so as to quickly obtain the analysis results of serum data. Research and propose an improved K-means algorithm to cluster data. Clustered data has the characteristics of small differences within clusters and large differences among clusters, which can better discretize continuous data. Apriori algorithm and FP Growth algorithm analyze and obtain association rules for serum mass spectrometry data and physical examination data, which can verify the accuracy of blood detection results. It is of great significance for the development of medical blood testing.

关 键 词：聚类 关联分析 APRIORI算法 质谱数据 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论] R-05[自动化与计算机技术—计算机科学与技术]